Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0047. Min Range: -1.0047

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1516660 (Python Code)

Max Activating Token Index: 723

Text #1

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6416. Min Act: 0.0000

Data Index: 1376180 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1646746 (Python Code)

Max Activating Token Index: 828

Text #3

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1404964 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1385093 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1477047 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1563870 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1448957 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1645402 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1603678 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1530678 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1482334 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1461945 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1390547 (Python Code)

Max Activating Token Index: 51

Text #14

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1615786 (Python Code)

Max Activating Token Index: 349

Text #15

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1412324 (Python Code)

Max Activating Token Index: 936

Text #16

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1509172 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1482422 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1563737 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1647046 (Python Code)

Max Activating Token Index: 754